AI-Driven Multi-Agent Simulation of Stratified Polyamory Systems: A Computational Framework for Optimizing Social Reproductive Efficiency

Yicai Xing

cs.AIMar 21, 2026

AI-Driven Multi-Agent Simulation of Stratified Polyamory Systems: A Computational Framework for Optimizing Social Reproductive Efficiency

Authors: Yicai Xing

Organizations: Independent Researcher

Abstract

Contemporary societies face a severe crisis of demographic reproduction. Global fertility rates continue to decline precipitously, with East Asian nations exhibiting the most dramatic trends -- China's total fertility rate (TFR) fell to approximately 1.0 in 2023, while South Korea's dropped below 0.72. Simultaneously, the institution of marriage is undergoing structural disintegration: educated women rationally reject unions lacking both emotional fulfillment and economic security, while a growing proportion of men at the lower end of the socioeconomic spectrum experience chronic sexual deprivation, anxiety, and learned helplessness. This paper proposes a computational framework for modeling and evaluating a Stratified Polyamory System (SPS) using techniques from agent-based modeling (ABM), multi-agent reinforcement learning (MARL), and large language model (LLM)-empowered social simulation. The SPS permits individuals to maintain a limited number of legally recognized secondary partners in addition to one primary spouse, combined with socialized child-rearing and inheritance reform. We formalize the A/B/C stratification as heterogeneous agent types in a multi-agent system and model the matching process as a MARL problem amenable to Proximal Policy Optimization (PPO). The mating network is analyzed using graph neural network (GNN) representations. Drawing on evolutionary psychology, behavioral ecology, social stratification theory, computational social science, algorithmic fairness, and institutional economics, we argue that SPS can improve aggregate social welfare in the Pareto sense. Preliminary computational results demonstrate the framework's viability in addressing the dual crisis of female motherhood penalties and male sexlessness, while offering a non-violent mechanism for wealth dispersion analogous to the historical Chinese Grace Decree (Tui'en Ling).

Figures & tables

Panel of Figure 1 — Figure 1: Long-term decline in total fertility rates (TFR) across major East Asian nations. Data: UN Population Division [ 1 ] , national statistical bureaus, Choe & Lee [ 2 ] .

Panel of Figure 2 — Figure 2: The dual dimensions of monogamy’s structural failure and their convergent effect on social reproduction. Each dimension is supported by key empirical literature.

Panel of Figure 3 — Figure 3: Distribution of mating systems among mammals. Based on phylogenetic analysis by Lukas & Clutton-Brock [ 53 ] . Strict monogamy accounts for only $\sim$ 9% of species.

Panel of Figure 4 — Figure 4: The three-channel biological model of love. Visual [ 64 , 76 ] , olfactory [ 77 , 78 ] , and behavioral [ 79 , 80 ] channels jointly constitute the genetic quality assessment system.

Tier	Composite Traits	Typical Profile	Under Monogamy
A	Resource-rich, physically/intellectually outstanding	Elite professionals, entrepreneurs, high-attractiveness individuals	Multi-dimensional needs constrained by single partner
B	Average composite attractiveness	Social majority	Partial preference for A-tier unattainable; limited satisfaction
C	Economically deprived, disadvantaged in appearance/social skills	Low-income, socially isolated	Some permanently unpartnered; welfare $\approx$ 0; instability risk [ 48 ]

Table 1: A/B/C Tier Model Overview (analytical tool, not institutional label)

Panel of Figure 5 — Figure 5: SPS institutional structure and rights system. The limited rights design for companions avoids equating secondary relationships with marriage while safeguarding children’s interests. Legal frameworks for multi-partner recognition are emerging [ 82 ] .

Panel of Figure 6 — Figure 6: Cross-tier partner network under SPS. Tier B’s multi-directional compatibility renders it the system’s buffer and connector layer, ensuring cross-tier flow of sexual and emotional resources. This model accords with Orians’ (1969) Polygyny Threshold Model [ 83 ] and Emlen & Oring’s (1977) ecological framework [ 16 ] .

Panel of Figure 7 — Figure 7: Intergenerational wealth dispersion comparison via the Grace Decree effect. SPS accelerates wealth dispersal by increasing the number of legitimate heirs of high-resource individuals.

Panel of Figure 8 — Figure 8: Pareto improvement argument. Under SPS, expected welfare improves across all tiers, with the most significant gains at Tier C. Values derived from theoretical model projections.

Panel of Figure 9 — Figure 9: Four independent pathways through which SPS promotes fertility recovery. Each pathway is supported by empirical literature.

Criticism	Argument	Response & Supporting Literature
Objectification of women	Multiple partners commodifies women	SPS is strictly gender-symmetric. Women hold identical polyamorous rights. Orians’ (1969) model [ 83 ] suggests polygamy may be advantageous for women under resource inequality
Inevitable jealousy	Polyamory necessarily produces jealousy	Conley et al. (2013) [ 25 ] : CNM relationships exhibit lower jealousy than infidelity within monogamy. Moors et al. (2017) [ 26 ] : polyamorous relationship satisfaction is comparable to monogamous relationships. Rubel & Bogaert (2015) [ 27 ] : CNM correlates with positive psychological well-being. Sheff (2014) [ 28 ] : ethnographic evidence of successful poly families
ABC is discriminatory	Tiering people is dehumanizing	A/B/C is a descriptive analytical tool (analogous to income quintiles in economics), not a basis for differential legal treatment. All individuals enjoy identical institutional rights. Becker’s (1973) [ 17 ] marriage market model already incorporates hierarchical structure
Undermines family	Weakened families harm children	Kibbutz research [ 87 ] : socialized child-rearing produces normal developmental outcomes. Golombok (2016) [ 89 ] : children in non-traditional families show no significant psychological developmental differences
Impractical	Cannot be implemented now	Directional framework requiring gradual implementation. See Section 9 . Emerging legal recognition of polyamorous partnerships [ 82 ] suggests institutional pathways are opening

Table 2: Principal criticisms of SPS and evidence-based responses

Panel of Figure 10 — Figure 10: Graduated implementation roadmap for SPS. Each phase builds upon the institutional foundations and social consensus established by its predecessor. Emerging legal recognition of polyamorous partnerships [ 82 ] suggests that Phase I is already partially underway in some jurisdictions.

Parameter	Value
Population size $N$	10,000 agents
Gender ratio	50:50
Tier distribution (A:B:C)	15:60:25
Simulation horizon	100 years (time steps)
Partner limit (SPS)	3 (1 spouse + 2 companions)
Partner limit (monogamy baseline)	1

Table 3: Proposed simulation parameters

From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling
Sep 28, 2026Wangxuan Fan, Xiaoyu Nie, Zhoutian Shi +5Agent-Based Modeling Large Language Model-Based Social Simulation
The Chinese University of Hong Kong, Shenzhen
From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations
Jul 7, 2026Shiyi Ling, Zhi Zheng, Hui Zheng +3Multi-Agent LLM Systems Human Behavior Simulation
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Anhui University · North Automatic Control Technology Institute +1
Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization
Aug 4, 2026Hadi Mohammadi, Tina Shahedi, Robert A. Bagheri +2Annotator Disagreement Preference Optimization
Department of Methodology and Statistics, Utrecht University, The Netherlands · Department of Information and Computing Sciences, Utrecht University, The Netherlands · Field Technology Innovations (FTI) & Robotics, Wageningen University & Research, The Netherlands

Sep 28, 2026J/K move · Enter open · S save

From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling

Wangxuan Fan, Xiaoyu Nie, Zhoutian Shi, Xiangcheng Meng+4

The Chinese University of Hong Kong, Shenzhen

Agent-Based Modeling Large Language Model-Based Social Simulation

Open paper AskPDF arXiv

Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and centralized computation, whereas many real-world matching processes are decentralized, asynchronous, and shaped by sequential interaction under limited information. We propose a dynamic bipartite matching framework that combines large language model (LLM) agents with contextual bandits. In a simulated Chinese marriage market, economically grounded LLM agents evaluate locally encountered candidates, while agent-specific Logistic-UCB models learn reciprocal acceptance from realized proposal outcomes. The mechanism therefore separates two decisions---whom do I like? and who is likely to like me back?---without requiring ex ante market-wide preference rankings. We first validate LLM-induced mate preferences against the empirical conditional-logit reference across multiple LLM backbones. In the

50\times50

matching experiment, Bandit-UCB achieves the highest mean mutual welfare (56.01 versus 54.87 for Gale--Shapley), a smaller gender rank gap than the classical baselines, and the fewest blocking pairs among the LLM-ABM policies. Learned acceptance models show economically interpretable gender-differentiated associations, while counterfactual setups reveal no systematic unilateral advantage from prior search knowledge. Overall, these results support the advantages of decentralized matching with LLM-based behavioral modeling and online learning under incomplete information for economic simulation and computational social science research.

Abstract

Explore similar work

From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization